Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How A.I. Conquered Poker

nytimes.com

Post reply on HN
Print view View original

111–120 of 188 posts

Re: How A.I. Conquered Poker

#111

Post by dwohnitmok »

runnerup wrote: post #100
dwohnitmok wrote: post #51

Earlier quoted context omitted.

I think this is purely a resource issue, e.g. if Google Brain decided to make an MtG bot I would be fairly confident it would be superhuman. Even real time strategy games like Starcraft are looking like they're on the cusp of superhuman bots (Alphastar was competitive as Protoss against elite players, but did not consistently beat them).

Alphastar also didn't play with the same limitations that a human has. Even after removing its ability to see the entire map and finally forcing it to scroll around, alphastar never misclicks (so its APM==EPM) and can still blast nearly unlimited APM for short bursts as long as its "average APM" over an x-second period matched human's APM. I believe Alphastar would generate more interesting strategies if we limited a…

> Alphastar also didn't play with the same limitations that a human has. Even after removing its ability to see the entire map and finally forcing it to scroll around, alphastar never misclicks (so its APM==EPM) and can still blast nearly unlimited APM for short bursts as long as its "average APM" over an x-second period matched human's APM. > I believe Alphastar would generate more interesting strategies if we limited alphastar to a bit below human APM...

No Alphastar definitely had misclicks, and it had a maximum cap on APM regardless of average that was far lower than the max burst of APM (or even EPM) of top players. When I have the time I can go dig up some games where Alphastar definitely has misclicks, and I believe the Deep Mind team has said before that it will misclick. Its APM limits are already lower than pros both on average and in bursts (and are reflected in its play, Alphastar will often mis-micro units in larger, more frantic battles such as allowing disruptor shots to destroy its own units, but it will never make the same mistake with much smaller numbers of units).

> Currently its main strategy is "perfectly juggle stalkers"

Definitely not. That was its strategy in its early iterations against MaNa and is no longer feasible with the stricter limitations in place. Its Protoss strategy is significantly more advanced than that now (see its impressive series of games against Serral with an amazing comeback here: https://www.youtube.com/watch?v=jELuQ6XEtEc and a powerful defense against multi-pronged aggression here: https://www.youtube.com/watch?v=C6qmPNyKRGw) (and of course by "now" I mean when Deep Mind took it off the ladder). Both of these involve an eclectic mix of units with Alphastar effectively using each type of unit and varying it in response to what Serral puts out and its own resource constraints.

A lot of commentators have difficulty distinguishing Alphastar from humans when the former plays as Protoss (its Terran and Zerg play is weaker and often more mechanical).

> I mean strategies that humans could learn to adopt.

My main takeaways from watching Alphastar were "pros undervalue static defense and often have a less than optimal number of workers (where Alphastar's seeming overproduction of workers lets it shrug off aggressive harassment)," but I don't know if those have picked up in the meta.

Re: How A.I. Conquered Poker

#112

Post by bluecalm »

evrydayhustling wrote: post #37
jstx1 wrote: post #27

But it hasn't conquered it! I kept searching the article for some new recent breakthrough that I've missed but it's not there. Yes, solvers like Pio have been around for years and limit holdem has been essentially solved for a while but nobody plays limit holdem anyway. The two most popular games (no-limit Texas holdem and pot-limit Omaha) are still unsolved.

There is still a lively academic community and major progress! Check out CMU's no limit results [1]. (I realize articles like this have to pick some angles to make it interesting, but it was weird to see only dated research mentioned.) But if you are rooting against the machines, don't worry: it is almost certainly impossible to calculate a full equilibrium policy for no limit multiplayer, so we will instead be debat…

It doesn't even matter if you can calculate multiplayer equilibrium. It's not the solution the same way it is in heads-up. You can still lose if you employ the equilibrium in multiplayer unlike in HU.

Re: How A.I. Conquered Poker

#113

Post by howdydoo »

noambrown wrote: post #38
jstx1 wrote: post #27

But it hasn't conquered it! I kept searching the article for some new recent breakthrough that I've missed but it's not there. Yes, solvers like Pio have been around for years and limit holdem has been essentially solved for a while but nobody plays limit holdem anyway. The two most popular games (no-limit Texas holdem and pot-limit Omaha) are still unsolved.

Bots are superhuman in no-limit Texas hold'em. Libratus beat top humans in two-player in 2017 and Pluribus beat top humans in six-player in 2019: https://www.science.org/doi/abs/10.1126/science.aao1733 https://www.science.org/doi/abs/10.1126/science.aay2400 It's shocking that the reporter didn't mention these results or anything else more recent than 2015.

I know that PioSolver is not a "poker AI" per se, but the article seems to say it can tell you what to do based on the table situation. Has anyone tried pitting pro players against PioSolver?

Re: How A.I. Conquered Poker

#114

Post by sillysaurusx »

bluecalm wrote: post #107
sillysaurusx wrote: post #84

Earlier quoted context omitted.

How did you end up working on this? It’s an interesting history.

I was always interested in math and encountered game theory concepts early in life. It's a perfect mix of being not a very good programmer, not a top math mind, not an exceptional poker player but still being all those things at the right time and place.

I really like that you got to do this, and that you turned your weaknesses into such a great strength. Thank you for showing that you don’t need to be exceptional in a specific area to do exceptional work. Best of luck with whatever you decide to pursue next.

Re: How A.I. Conquered Poker

#115

Post by howdydoo »

bloodyplonker22 wrote: post #90
cortesoft wrote: post #65

Earlier quoted context omitted.

I would expect bots to add random delays? They could even determine real player delay distributions and emulate that.

yes, that is the obvious step that bot makers have taken. When bots were barely at the online poker scene, nobody cared to even check. Of course, there are still other ways to check for bots such as a user playing for an unreasonable amount of time or an extraordinary amount of tables, or simply not answering to chat.

The natural next step is adding ELIZA-like chat responses to your bots

Re: How A.I. Conquered Poker

#116

Post by magixx »

splonk wrote: post #104
sillysaurusx wrote: post #83

Earlier quoted context omitted.

So how much have you won and lost in total? I don’t have any knowledge of poker, so I don’t know how to ballpark this. And the impersonal questions are boring after seven lifetimes, so I thought I’d ask. It would be interesting to see a GitHub style graph of poker activity, with won and lost corresponding to added lines and removed lines.

6 figures. Turns out there's a lot more (and less risky) money in software development than there is in poker. I gave up the professional poker life pretty early and actually made quite a lot more as a talented "amateur" with a Silicon Valley software dev salary that took away the risk of ruin constraints I had a pro. Plus I didn't really enjoy playing professionally anyways - it's pretty mindnumbingly boring to play…

I imagine that for pro players to play at their best can be taxing and wouldn't be surprised if some just wanted to play less costly games for more what they could deem to be more fun.

Re: How A.I. Conquered Poker

#117

Post by noambrown »

bluecalm wrote: post #112
evrydayhustling wrote: post #37

Earlier quoted context omitted.

There is still a lively academic community and major progress! Check out CMU's no limit results [1]. (I realize articles like this have to pick some angles to make it interesting, but it was weird to see only dated research mentioned.) But if you are rooting against the machines, don't worry: it is almost certainly impossible to calculate a full equilibrium policy for no limit multiplayer, so we will instead be debat…

It doesn't even matter if you can calculate multiplayer equilibrium. It's not the solution the same way it is in heads-up. You can still lose if you employ the equilibrium in multiplayer unlike in HU.

That's not true in practice for poker. Pluribus showed that if you run CFR in multiplayer poker you get a solution that works great in practice. Multiple equilibria are certainly a theoretical issue for many games, but poker conveniently isn't one of them.

Re: How A.I. Conquered Poker

#118

Post by jeffreyrogers »

howdydoo wrote: post #113
noambrown wrote: post #38

Earlier quoted context omitted.

Bots are superhuman in no-limit Texas hold'em. Libratus beat top humans in two-player in 2017 and Pluribus beat top humans in six-player in 2019: https://www.science.org/doi/abs/10.1126/science.aao1733 https://www.science.org/doi/abs/10.1126/science.aay2400 It's shocking that the reporter didn't mention these results or anything else more recent than 2015.

I know that PioSolver is not a "poker AI" per se, but the article seems to say it can tell you what to do based on the table situation. Has anyone tried pitting pro players against PioSolver?

PioSolver requires putting in the hand range of the opponent, so the quality of PioSolver's solution is largely down to how accurate the guess at that hand range is. But if a pro knows he is playing against PioSolver configured with a certain hand range he can just change his strategy to adapt. In theory though if PioSolver knows the correct hand range then it shouldn't be possible to any better than tie given enough hands.

Re: How A.I. Conquered Poker

#119

Post by jeffreyrogers »

throwaway_Aef8 wrote: post #103
tziki wrote: post #98

Earlier quoted context omitted.

No limit holdem has been essentially solved. Pluribus & co not withstanding, you just haven't heard of it because the people who have solved it are busy printing money in online poker (yes, I know they try to detect bots, and no, they can't detect them all). With stakes this high, academic progress lags the 'actual' state-of-the-art by years.

IIRC it's "solved" for heads up but not really multiway like 3+ to the flop. I believe in a recent Bart Hanson Youtube he points out that mutltiway is not solved.

It's not solved for multiway in the sense that the optimal move in each situation isn't known, but there are AIs like Pluribus that have superhuman performance.

Re: How A.I. Conquered Poker

#120

Post by hashberry »

HALtheWise wrote: post #8
hashberry wrote: post #2

> he opened a computer program called PioSOLVER, one of a handful of artificial-intelligence-based tools So I checked out this tool, and the team describes themselves as "programmers interested in algorithms"[0] ... what is the difference between A.I. and algorithms? [0] https://www.piosolver.com/pages/about-us

The taxonomy I personally use is: * Every computer program has algorithms, it's an extremely general term for "the idea behind how the computer will solve the problem". Advanced algorithms are typically those that took a lot of human effort to come up with. * Machine Learning refers to a specific class of algorithms where the computer automatically figures out (part of) what it should do based on data. * Deep learnin…

I like your taxonomy. But just to clarify: is the cruise control on my car "artificial intelligence?" Because a lot of dumb 15-year-old teenagers don't know they have to increase power while going up a hill, while my cruise control algorithm does.
Post reply on HN